Microsoft patents method to feed compressed video data to AI models
Microsoft describes a system that takes compressed media files, like videos, and only partially unpacks them to extract specific data structures called syntax elements. These elements are then converted into tokens, a format that generative AI models can understand, allowing the AI to learn from or process the media without fully decompressing the entire file.
In the filing’s own words
A computer system performs operations to prepare input to a generative artificial intelligence (“AI”) model. The system receives compressed data for media, which has been compressed according to a media compression format to produce the compressed data. The system partially decompresses the compressed data (e.g., performing parsing and entropy decoding operations). This produces syntax elements of the compressed data according to the media compression format. The system converts the syntax elements into tokens that represent the syntax elements, respectively. Unlike the syntax elements (in the media compression format), the tokens are encoded in an input format for the generative AI model. The system stores the tokens in memory or storage, from which the system can provide the tokens to the generative AI model for use in a training process or inference process for media synthesis, media compression, media decompression, or another purpose.
What exactly they claim (claim 1)
1. One or more non-transitory computer-readable media having stored thereon computer-executable instructions for causing a processor system, when programmed thereby, to perform operations comprising: receiving compressed data for media, the media having been compressed according to a media compression format to produce the compressed data; partially decompressing the compressed data, thereby producing syntax elements of the compressed data according to the media compression format; converting the syntax elements into tokens that represent the syntax elements, respectively, wherein the tokens are encoded in an input format for a generative artificial intelligence (“AI”) model, and wherein, for a given syntax element among the syntax elements, a given token among the tokens indicates a syntax structure that includes the given syntax element, a type of the given syntax element, and a value of the given syntax element; and storing the tokens in memory or storage.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- Partial decompression of compressed media for input to a generative artificial intelligence model
- Patent number
- US12732626B2
- Application number
- 18421858
- Filed
- Jan 24, 2024
- Granted
- Sep 8, 2026
- Inventors
- 2
- Claims
- 20
Classified under
H04N 19/42 Electricity & electronicsH04N 19/13 Electricity & electronicsH04N 19/167 Electricity & electronicsH04N 19/70 Electricity & electronicsMore from Microsoft in AI & software
- Microsoft patents method to check AI answers against verified facts Oct 20, 2026
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.